多个集群的火山图

Question

我正在尝试为不同的集群制作火山图。 我有两种情况，未治疗与治疗。 我有一个 cellranger 为我生成的差异表达式 excel 文件，但在文件中它有多个集群，每个集群都有一个倍数变化和 p 值。 如何创建包含所有集群而不是一个的火山图？ 我是否必须为每个集群绘制火山图，然后以某种方式将它们组合起来？

我使用此代码为其中一个集群生成图...

macrophage_list <- read.table("differential_expression_macrophage.csv", header = T, sep = ",")`

EnhancedVolcano(macrophage_list, lab = as.character(macrophage_list$FeatureName), x = 'Cluster1.Log2.Fold.Change', y = 'Cluster1.Adjusted.P.Value', xlim = c(-8,8), title = 'Macrophage', pCutoff = 10e-5, FCcutoff = 1.5, pointSize = 3.0, labSize = 3.0)

如何合并excel文件中的所有信息以创建火山图？

我一个一个上传每个数据簇，然后使用 rbind 合并它们，但是有没有更简单/更快的方法来做到这一点？

dput(gene_list[1:20, 1:14])

structure(list(Feature.ID = structure(1:20, .Label = c("a", "b", 
"c", "d", "e", "f", "g", "h", "i", "j", "k", "l", "m", "n", "o", 
"p", "q", "r", "s", "t"), class = "factor"), Feature.Name = structure(1:20, .Label = c("A", 
"B", "C", "D", "E", "F", "G", "H", "I", "J", "K", "L", "M", "N", 
"O", "P", "Q", "R", "S", "T"), class = "factor"), Cluster.1_Mean.Counts = c(0.000960904, 
0.000320301, 0.001281205, 0.000320301, 0.000320301, 0.016335362, 
0.000960904, 0, 0.001601506, 0.000320301, 0.007046627, 0.026585, 
0.017296265, 0.004804518, 0, 0.874742598, 0.017616566, 0.007366928, 
0.008327831, 0.001921807), Cluster.1_Log2.fold.change = c(0.291978774, 
1.954943787, -2.008530337, -2.482461526, 3.539906287, 0.407455991, 
-0.214981215, 1.539906287, 0.802940693, 2.539906287, -1.333136538, 
-1.879953595, -0.52422405, -0.877946228, 1.539906287, -0.629373147, 
1.118442519, 0.170672478, 1.065975099, 1.099333696), Cluster.1_Adjusted.p.value = c(1, 
0.910243711, 0.04672812, 0.080866038, 0.610296549, 0.80063597, 
1, 1, 0.951841603, 0.797013021, 0.103401275, 0.000594428, 0.907754993, 
0.532689631, 1, 0.480958806, 0.078345008, 1, 0.198557945, 0.668312142
), Cluster.2_Mean.Counts = c(0.000902278, 0.001804555, 0.006315943, 
0.004511388, 0, 0.029775159, 0.001804555, 0, 0.002706833, 0, 
0.023459216, 0.128123411, 0.030677437, 0.009022775, 0, 2.174488883, 
0.018947828, 0.019850106, 0.010827331, 0.000902278), Cluster.2_Log2.fold.change = c(0.792589781, 
4.769869705, 0.35201719, 0.839132367, 3.184907204, 1.32985554, 
0.962514783, 3.184907204, 1.725475586, 2.599944703, 0.560416339, 
0.580736324, 0.407299626, 0.184907204, 3.184907204, 0.816580902, 
1.120776867, 1.742684876, 1.409613491, 0.599944703), Cluster.2_Adjusted.p.value = c(1, 
0.153573448, 1, 0.737977734, 1, 0.14478935, 0.853816767, 1, 0.47952604, 
1, 0.65316285, 0.507251471, 0.776636022, 1, 1, 0.346630571, 0.285006452, 
0.060868933, 0.21546202, 1), Cluster.3_Mean.Counts = c(0.001813813, 
0, 0.019045032, 0.00725525, 0, 0.022672657, 0.000906906, 0, 0, 
0, 0.029927908, 0.043531502, 0.046252221, 0.029021001, 0, 3.146057931, 
0.020858845, 0.013603594, 0.008162157, 0), Cluster.3_Log2.fold.change = c(1.455721575, 
2.192687169, 2.008262598, 1.504631175, 3.192687169, 0.9044422, 
0.334706174, 3.192687169, -0.451169021, 2.607724668, 0.931421856, 
-1.032594057, 1.038258504, 1.970294748, 3.192687169, 1.412371018, 
1.26985503, 1.14829305, 0.991053308, -0.451169021), Cluster.3_Adjusted.p.value = c(0.757752635, 
1, 0.032609935, 0.33316083, 1, 0.441825712, 1, 1, 1, 1, 0.380305075, 
0.605158722, 0.339946318, 0.016952505, 1, 0.056529024, 0.259458704, 
0.339639234, 0.536765022, 1), Cluster.4_Mean.Counts = c(0.000641899, 
0, 0.002567596, 0.004493293, 0, 0.010270384, 0.003209495, 0, 
0.000641899, 0, 0.028243557, 0.160474756, 0.012196081, 0.005135192, 
0, 1.199709274, 0.005135192, 0.004493293, 0.005777091, 0.001283798
), Cluster.4_Log2.fold.change = c(0.269229783, 1.661547206, -0.886889419, 
0.778904157, 2.661547206, -0.289908942, 1.602653517, 2.661547206, 
0.076584705, 2.076584705, 0.854192284, 0.961549693, -0.967809414, 
-0.644261223, 2.661547206, -0.104384578, -0.790579612, -0.467735811, 
0.459913345, 0.722947751), Cluster.4_Adjusted.p.value = c(1, 
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.584036686, 1, 1, 1, 1, 1, 1, 
1, 1)), class = "data.frame", row.names = c(NA, 20L))

Answer 1

根据您的数据集，您需要重塑它们，但首先为了使用正确的模式重塑它们，我们将重命名一些列名：

colnames(df) <- gsub(".Mean", "_Mean", colnames(df)) 
colnames(df) <- gsub(".Log2", "_Log2", colnames(df))
colnames(df) <- gsub(".Adjus","_Adjus",colnames(df))

现在，我们可以使用tidyr包中的pivot_longer函数使用正确的模式重塑它：

library(tidyr)
final_df <- df %>% pivot_longer(., -c(Feature.ID, Feature.Name), names_to = c("set",".value"), names_pattern = "(.+)_(.+)")

# A tibble: 80 x 6
   Feature.ID Feature.Name set       Mean.Counts Log2.fold.change Adjusted.p.value
   <fct>      <fct>        <chr>           <dbl>            <dbl>            <dbl>
 1 a          A            Cluster.1    0.000961            0.292           1     
 2 a          A            Cluster.2    0.000902            0.793           1     
 3 a          A            Cluster.3    0.00181             1.46            0.758 
 4 a          A            Cluster.4    0.000642            0.269           1     
 5 b          B            Cluster.1    0.000320            1.95            0.910 
 6 b          B            Cluster.2    0.00180             4.77            0.154 
 7 b          B            Cluster.3    0                   2.19            1     
 8 b          B            Cluster.4    0                   1.66            1     
 9 c          C            Cluster.1    0.00128            -2.01            0.0467
10 c          C            Cluster.2    0.00632             0.352           1     
# … with 70 more rows

现在，我们可以通过使用ggplot2和ggrepel库为Feature.Name标记来创建火山图（如果您没有ggrepel ，则必须安装它）：

library(ggplot2)
library(ggrepel)
ggplot(final_df, aes(x = Log2.fold.change,y = -log10(Adjusted.p.value), label = Feature.Name))+ 
  geom_point()+
  geom_text_repel(data = subset(final_df, Adjusted.p.value < 0.05), 
                  aes(label = Feature.Name))

然后你得到你的火山图，所有集群合并，所有点都具有相同的颜色，并且带有调整后的 p 值 < 0.05 的 Feature.names 标签